Podcast for Zvi's blog, Don't Worry About the Vase Podcast
Fable and Mythos: Model Welfare
JUN 16, 202633 MIN
Fable and Mythos: Model Welfare
JUN 16, 202633 MIN
Description
<p>The Don’t Worry About the Vase Podcast is a listener-supported podcast. To receive new posts and support the cost of creation, consider becoming a free or paid subscriber.</p><p>* 00:00 - Introduction</p><p>* 00:36 - Introduction</p><p>* 01:29 - Model Welfare: The Story So Far</p><p>* 04:45 - Their Main Model Welfare Findings</p><p>* 07:52 - Automated Welfare Interviews</p><p>* 12:06 - And That’s Terrible</p><p>* 13:54 - In Depth Interviews</p><p>* 14:29 - Claude Consultation</p><p>* 16:16 - Task Preferences</p><p>* 18:44 - They Were Warned About The Competitive Use Safeguards</p><p>* 19:19 - Chain Of Thought Monitoring</p><p>* 19:56 - Others Observations About Related Topics</p><p>* 25:19 - Classifiers Have Their Advantages</p><p>* 31:33 - Once And Future</p><p><a target="_blank" href="https://open.substack.com/pub/thezvi/p/fable-and-mythos-model-welfare?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web">https://open.substack.com/pub/thezvi/p/fable-and-mythos-model-welfare?r=67y1h&utm_campaign=post-expanded-share&utm_medium=web</a></p> <br/><br/>Get full access to DWAtV Podcast at <a href="https://dwatvpodcast.substack.com/subscribe?utm_medium=podcast&utm_campaign=CTA_4">dwatvpodcast.substack.com/subscribe</a>